Analysis, Implementation and Comparison of Machine Learning Algorithms on Breast Cancer Dataset using WEKA Tool
K. Srikanth1, S. Zahoor Ul Huq2, A.P. Siva Kumar3
1K. Srikanth, Research Scholar, Department of Computer Science & Engineering, JNTUA, Anantapuramu (Andhra Pradesh), India.
2S. Zahoor Ul Huq, Professor, Department of Computer Science & Engineering, G.Pulla Reddy Engineering College, Kurnool (Andhra Pradesh), India.
3A.P. Siva Kumar, Assistant Professor, Department of Computer Science & Engineering, JNTUA, Anantapuramu (Andhra Pradesh), India.
Manuscript received on 23 March 2019 | Revised Manuscript received on 04 April 2019 | Manuscript Published on 18 April 2019 | PP: 330-333 | Volume-7 Issue-6S March 2019 | Retrieval Number: F02650376S19/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In modern world among the fatal diseases, cancer is at the peak level. The reasons for cancer disease are modern lifestyle, environment factors or genetic factors. Cancer has become the prime reason of death in developed countries. Among the leading cancers, Breast cancer is at the top in the women. In women, breast cancer is one of the major causes of death. Cancer examination is generally experimental and/or natural in nature. To mine significant data patterns, Data mining acts prominent role in information detection. In data mining applications, forecasting the output of a disease is a major challenge. In this paper, a performance comparison between different machine learning algorithms: Sequential Minimal Optimization (SMO), Naive Bayes (NB), J48 (C4.5 decision tree), K-Means, K-Nearest Neighbours (k-NN) has been performed. To measure the performance of these algorithms, Wisconsin Breast Cancer (Original) dataset has been taken. The main intention is to measure the competence of each algorithm based on precision, specificity, sensitivity and accuracy. Investigated outcomes prove that SMO tops among the list in terms of correctness and low fault rate. All experiments are performed and implemented using WEKA tool.
Keywords: Breast Cancer, Data Mining, Machine Learning, WEKA.
Scope of the Article: Machine Learning